On incorporating subjective interestingness into the mining process

Subjective interestingness is at the heart of the successful discovery of association rules. To determine what is subjectively interesting, users´ domain knowledge must be applied. The author (1999) introduced an approach that requires very little domain knowledge and interaction to eliminate the majority of the rules that are subjectively not interesting. In this paper we investigate how this approach can be incorporated into the mining process, the benefits and disadvantages of doing so, and examine the results of its application to real databases.